AI Paper Atlas

Research map / Image generation / Editing and style transfer

SSCGAN: Facial Attribute Editing via Style Skip Connections

Wenqing Chu, Ying Tai, Chengjie Wang, Jilin Li, Feiyue Huang, Rongrong Ji

ECCV 2020 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 21 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add style skip connections to spatial-only model (ablation)SSCGAN · CelebA testaverage attribute generation accuracy (%): 82.46 -> 94.21Improved
add spatial information transfer to style-only model (ablation)SSCGAN · CelebA testaverage attribute generation accuracy (%): 92.26 -> 94.21Improved
add style skip connections instead of spatial only (ablation)SSCGAN · CelebA testaverage attribute generation accuracy (%): 82.46 -> 92.26Improved
predict style from encoder style plus attribute difference with residual learning, not attribute difference alone (ablation)SSCGAN · CelebA testaverage attribute generation accuracy (%): 90.03 -> 94.21Improved
use style features from every block rather than only the last encoder stage (ablation)SSCGAN-mm vs SSCGAN-lm · CelebA testaverage attribute generation accuracy (%): 87.08 -> 87.60Improved
use both mean and variance instead of mean only (ablation)SSCGAN-lmv vs SSCGAN-lm · CelebA testaverage attribute generation accuracy (%): 87.08 -> 88.07Improved
add residual learning to per-block style embedding (ablation)SSCGAN-mm · CelebA testaverage attribute generation accuracy (%): 87.60 -> 94.21Improved
use multiple skip connections instead of one at 16x16 (ablation)SSCGAN-16 · CelebA testaverage attribute generation accuracy (%): 93.63 -> 94.21Improved
use multiple skip connections instead of one at 128x128 (ablation)SSCGAN-128 · CelebA testaverage attribute generation accuracy (%): 77.79 -> 94.21Improved
use multiple skip connections instead of one at 8x8 (ablation)SSCGAN-8 · CelebA testaverage attribute generation accuracy (%): 88.28 -> 94.21Improved
use SSCGAN instead of STGANfacial attribute editing · CelebA testaverage attribute generation accuracy (%): 83.21 -> 94.21Improved
use SSCGAN instead of STGANfacial attribute editing · CelebA testFID: 4.78 -> 4.69Improved

Later papers that compared with this method

2 later accepted papers report SSC-GAN as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy